code-evaluation

Klipse is a JavaScript plugin for embedding interactive code snippets in tech blogs.

Pip compatible CodeBLEU metric implementation available for linux/macos/win

Industrial-level evaluation benchmarks for Coding LLMs in the full life-cycle of AI native software developing.企业级代码大模型评测体系,持续开放中

💯 Exerciseur / outils d'évaluation d'étudiants -- NOT MAINTAINED ANYMORE

An agent evaluation framework with native multi-turn feedback iteration.

Backend for automated evaluation of programming tasks in higher education

Serapis Code Evaluator API - POC

AI-assisted programming education platform for universities, combining code evaluation, guided learning, restricted execution, and learning analytics.

.NET 10 backend for a mini code-evaluation platform. Users submit C#, Python or JavaScript solutions via a REST API; submissions are graded asynchronously against a simple rubric (security check, compiles/parses, passes a test) using background jobs. Clean Architecture, EF Core + PostgreSQL, Swagger, API-key auth, Docker.

💎 Sinatra server for running Rspec tests within Mumuki

SocratiQ AI uses socratic method of teaching to guide users through learning, asking questions that prompt critical thinking and problem-solving rather than providing direct answers.

An online based IDE to execute code made using React

Frontend for the Codemaze backend

A web-based exam platform for programming courses. Students solve Python problems in a browser-based IDE with Monaco editor, and their code is graded automatically inside sandboxed Docker containers.

Runs JavaScript, TypeScript, CoffeeScript, and LiveScript directly in Atom

An open-source Python library for code encryption, decryption, and safe evaluation using Python's built-in AST module, complete with allowed functions, variables, built-in imports, timeouts, and blocked access to attributes.

Python library to interact synchronously and asynchronously with tio.run

A Django-powered online coding assignment and automated evaluation platform with role-based authentication, leaderboards, and student dashboards.

A production-ready worker service for secure, isolated code execution. Consumes submissions from Kafka, executes programs in Docker containers with resource limits, and publishes results. Supports Python, Go, C, C++, and Java with horizontal scaling.

Automated evaluation pipeline for Linux character-device drivers (including LLM-generated ones): compiles, checks kernel style via checkpatch, runs security heuristics, and emits a weighted score as JSON.